Commit baac167b authored Jun 26, 2014 by Jesper Dangaard Brouer Committed by David S. Miller Jul 01, 2014

pktgen: avoid expensive set_current_state() call in loop



Avoid calling set_current_state() inside the busy-loop in
pktgen_thread_worker().  In case of pkt_dev->delay, then it is still
used/enabled in pktgen_xmit() via the spin() call.

The set_current_state(TASK_INTERRUPTIBLE) uses a xchg, which implicit
is LOCK prefixed.  I've measured the asm LOCK operation to take approx
8ns on this E5-2630 CPU.  Performance increase corrolate with this
measurement.

Performance data with CLONE_SKB==100000, rx-usecs=30:
 (single CPU performance, ixgbe 10Gbit/s, E5-2630)
 * Prev:  5454050 pps --> 183.35ns (1/5454050*10^9)
 * Now:   5684009 pps --> 175.93ns (1/5684009*10^9)
 * Diff:  +229959 pps -->  -7.42ns

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

parent 9ceb87fc

net/core/pktgen.c

+3 −6

Original line number	Diff line number	Diff line
		@@ -3407,10 +3407,10 @@ static int pktgen_thread_worker(void *arg)

		pr_debug("starting pktgen/%d: pid=%d\n", cpu, task_pid_nr(current));

		set_current_state(TASK_INTERRUPTIBLE);

		set_freezable();

		__set_current_state(TASK_RUNNING);

		while (!kthread_should_stop()) {
		pkt_dev = next_to_run(t);

		@@ -3424,8 +3424,6 @@ static int pktgen_thread_worker(void *arg)
		continue;
		}

		__set_current_state(TASK_RUNNING);

		if (likely(pkt_dev)) {
		pktgen_xmit(pkt_dev);

		@@ -3456,9 +3454,8 @@ static int pktgen_thread_worker(void *arg)
		}

		try_to_freeze();

		set_current_state(TASK_INTERRUPTIBLE);
		}
		set_current_state(TASK_INTERRUPTIBLE);

		pr_debug("%s stopping all device\n", t->tsk->comm);
		pktgen_stop(t);

Admin message